Predicting Postoperative Lung Cancer Recurrence and Survival Using Cox Proportional Hazards Regression and Machine Learning

Abstract

Background: Surgical resection remains the standard treatment for early-stage lung cancer. However, the recurrence rate after surgery is unacceptably high, ranging from 30% to 50%. Despite extensive efforts, accurately predicting the likelihood and timing of recurrence remains a significant challenge. This study aims to predict postoperative recurrence by identifying novel image biomarkers from preoperative chest CT scans.

Methods: A cohort of 309 patients was selected from 512 non-small-cell lung cancer patients who underwent lung resection. Cox proportional hazards regression analysis was employed to identify risk factors associated with recurrence and was compared with machine learning (ML) methods for predictive performance. The goal is to improve the ability to predict the risk and time of recurrence in seemingly "cured" patients, enabling personalized surveillance strategies to minimize lung cancer recurrence.

Results: The Cox hazards analyses identified surgical procedure, TNM staging, lymph node involvement, body composition, and tumor characteristics as significant determinants of recurrence risk, both for local/regional and distant recurrence, as well as recurrence-free survival (RFS) and overall survival (OS) (p < 0.05). ML models and Cox models exhibited comparable predictive performance, with an area under the receiver operative characteristic (ROC) curve (AUC) ranging from 0.75 to 0.77.

Conclusions: These promising findings demonstrate the feasibility of predicting postoperative lung cancer recurrence and survival time using preoperative chest CT scans. However, further validation using larger, multisite cohort is necessary to ensure robustness and facilitate integration into clinical practice for improved cancer management.

Keywords: CT biomarkers; Cox regression; lung cancer recurrence; machine learning; risk prediction.

Figure 1

Multi-level radiomics strategy.

Figure 2

Automated segmentation of body tissue by CNN-based models and manual segmentation on a whole-body PET-CT scan. (a) The original CT image, (b) the manual annotations of the body tissues, and (c) the computer segmentations of the body tissues. (d,e) The 3D visualization of the five body tissues.

Figure 3

Segmentation of various lung structures. (a) The original CT image; (b–f) the 3D visualization of segmented lungs, lobes, emphysema densities, airways, and pulmonary arteries and veins.

Figure 4

Segmentation of lung tumors on CT images. (a,d) The original CT images, (b,f) the contour of segmented tumors on the enlarged CT images, and (c,e) the 3D visualization of segmented tumors and surrounding areas.

Figure 5

Kaplan–Meier curves for the recurrence-free survival (RFS) and the overall survival (OS) of the lung cancer patients after surgery: (a) overall RFS, (b,c) RFS grouped by regions and organs, respectively, and (d,e) OS grouped by regions and organs, respectively.

Figure 5

Kaplan–Meier curves for the recurrence-free survival (RFS) and the overall survival (OS) of the lung cancer patients after surgery: (a) overall RFS, (b,c) RFS grouped by regions and organs, respectively, and (d,e) OS grouped by regions and organs, respectively.

Figure 6

ROC curves of the computer models to identify patients who did or did not experience postoperative lung cancer recurrence within 2 and 5 years.